Thierry Gourdin

Learn More
Factored Markov Decision Processes is the theoretical framework underlying multi-step Learning Classifier Systems research. This framework is mostly used in the context of Two-stage Bayes Networks, a subset of Bayes Networks. In this paper, we compare the Learning Clas-sifier Systems approach and the Bayes Networks approach to factored Markov Decision(More)
Video games are highly non-stationary environments. Our goal is to build a navigation module for video games based on Continuous Reinforcement Learning techniques. A study of the state-of-the-art of these techniques reveals that memory-based approaches are particularly suitable for our application context. More precisely, among memory-based reinforcement(More)
  • 1